<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-seeing">
    <titleInfo>
        <title>Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ran</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Miryam</namePart>
        <namePart type="family">de Lhoneux</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wessel</namePart>
        <namePart type="family">Poelman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Pixel-based language models (LMs) replace traditional tokenizers by processing rendered images of text, making cross-lingual transfer heavily dependent on the visual and structural properties of writing systems. However, the dynamics of adapting these models to low-resource languages with complex morphology and written in unique scripts are not yet explored. Using Tibetan as a case study, we analyze how continued pre-training of pixel-based LMs is influenced by data scale, initial script exposure, and cross-lingual transfer from languages written in other Brahmic scripts. We introduce four rendering-level metrics to quantify visual script similarity. We evaluate downstream performance across three tasks. Our results show that higher orthographic proximity enhances semantic transfer, even under severe data constraints. Additionally, we find a performance asymmetry based on the pre-training starting point: while multilingual pre-training (PIXEL-M4) has stronger initial performance, its capacity for subsequent adaptation seems to be constrained, whereas adapting a monolingual model (PIXEL) with mixed scripts yields more gains on sentence-level tasks. Our metrics and case study offer empirical observations that could help inform data selection and script adaptation choices when working with pixel-based models in similar low-resource settings.</abstract>
    <identifier type="citekey">zhang-etal-2026-seeing</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1509/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>34454</start>
            <end>34471</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation
%A Zhang, Ran
%A de Lhoneux, Miryam
%A Poelman, Wessel
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F zhang-etal-2026-seeing
%X Pixel-based language models (LMs) replace traditional tokenizers by processing rendered images of text, making cross-lingual transfer heavily dependent on the visual and structural properties of writing systems. However, the dynamics of adapting these models to low-resource languages with complex morphology and written in unique scripts are not yet explored. Using Tibetan as a case study, we analyze how continued pre-training of pixel-based LMs is influenced by data scale, initial script exposure, and cross-lingual transfer from languages written in other Brahmic scripts. We introduce four rendering-level metrics to quantify visual script similarity. We evaluate downstream performance across three tasks. Our results show that higher orthographic proximity enhances semantic transfer, even under severe data constraints. Additionally, we find a performance asymmetry based on the pre-training starting point: while multilingual pre-training (PIXEL-M4) has stronger initial performance, its capacity for subsequent adaptation seems to be constrained, whereas adapting a monolingual model (PIXEL) with mixed scripts yields more gains on sentence-level tasks. Our metrics and case study offer empirical observations that could help inform data selection and script adaptation choices when working with pixel-based models in similar low-resource settings.
%U https://aclanthology.org/2026.emnlp-main.1509/
%P 34454-34471

Markdown (Informal)

[Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation](https://aclanthology.org/2026.emnlp-main.1509/) (Zhang et al., EMNLP 2026)

• Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation (Zhang et al., EMNLP 2026)

ACL

• Ran Zhang, Miryam de Lhoneux, and Wessel Poelman. 2026. Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 34454–34471, Budapest, Hungary. Association for Computational Linguistics.